Open jeremyrcoyle opened 1 year ago
live_demo.py uses a TAPIR model, but it looks like you're using a TAP-Net config. What checkpoint file are you trying to use with that code? Did you perhaps intend to use a TAPIR config?
I'm using the checkpoint from https://storage.googleapis.com/dm-tapnet/causal_tapir_checkpoint.npy
. I see that above I'm referencing a TAP-Net config, so I tried again with a TAPIR config, and got the same error.
Please let me know if there is any more info I can provide or debugging steps on my end.
Is it an option to use the code snippet we provide for inference in the colab?
Has the error message changed from using the tapir config? The traceback you provided above has tap_net/ as the prefix for the variable names; it should be tapir if you're actually running a tapir model. Without more information it's difficult to guess why that's happening.
Did you solve the problem, I had the same thing happen to me.
I am getting same error... Is there any solution??
I am getting same error... Is there any solution??
I found the problem. you shoud have checkpoint.npy file in checkpoint path.
wget https://storage.googleapis.com/dm-tapnet/checkpoint.npy -o tapnet/checkpoint/checkpoint.npy
I am getting same error... Is there any solution??
I found the problem. you shoud have checkpoint.npy file in checkpoint path.
wget https://storage.googleapis.com/dm-tapnet/checkpoint.npy -o tapnet/checkpoint/checkpoint.npy
Also, this is a different checkpoint than in
I'm using the checkpoint from
https://storage.googleapis.com/dm-tapnet/causal_tapir_checkpoint.npy
. I see that above I'm referencing a TAP-Net config, so I tried again with a TAPIR config, and got the same error.
Using https://storage.googleapis.com/dm-tapnet/checkpoint.npy
, I got it to work with the experiment script.
I am getting same error... Is there any solution??
I found the problem. you shoud have checkpoint.npy file in checkpoint path.
wget https://storage.googleapis.com/dm-tapnet/checkpoint.npy -o tapnet/checkpoint/checkpoint.npy
Also, this is a different checkpoint than in
I'm using the checkpoint from
https://storage.googleapis.com/dm-tapnet/causal_tapir_checkpoint.npy
. I see that above I'm referencing a TAP-Net config, so I tried again with a TAPIR config, and got the same error.Using
https://storage.googleapis.com/dm-tapnet/checkpoint.npy
, I got it to work with the experiment script.
I try your method.But another error occurs: Traceback (most recent call last): File "/home/jishengyin/anaconda3/envs/tapnet/lib/python3.10/site-packages/numpy/lib/npyio.py", line 465, in load return pickle.load(fid, **pickle_kwargs) _pickle.UnpicklingError: invalid load key, '-'.
I am getting same error... Is there any solution??
I found the problem. you shoud have checkpoint.npy file in checkpoint path.
wget https://storage.googleapis.com/dm-tapnet/checkpoint.npy -o tapnet/checkpoint/checkpoint.npy
Also, this is a different checkpoint than in
I'm using the checkpoint from
https://storage.googleapis.com/dm-tapnet/causal_tapir_checkpoint.npy
. I see that above I'm referencing a TAP-Net config, so I tried again with a TAPIR config, and got the same error.Using
https://storage.googleapis.com/dm-tapnet/checkpoint.npy
, I got it to work with the experiment script.
I would like to evaluate a model. evaluation means first train a model and then evaluate it in evaluation dataset.(maybe).It means it doesn't need a pretrained model.So I can't understand why I got the error.
When invoking
experiment.py
to do inference:I get the following error:
Attempting to use a local GPU. The
live_demo.py
script works for me, so not sure what the issue is here.